SHAP Explainability Report — Multilingual Hate Speech Detection
Models: v1 (6 strategies, 8 epochs/phase) + v2 (Hinglish→Hindi→English→Full, 50 epochs/phase)
Explainer: shap.GradientExplainer on embedding sub-model (BiLSTM → output)
Background: 200 random training samples
Test samples per eval: 500 per language / full set
Table of Contents
- Methodology
- v1 — All 6 Strategies
- v2 — Hinglish → Hindi → English → Full
- Cross-Model Comparison
- Key Findings
1. Methodology
How SHAP Works Here
Standard SHAP cannot directly handle a Keras Embedding layer with integer token inputs because gradients cannot flow through integer operations. We solve this by splitting the model into two parts:
Original model:
Integer tokens (n, 100) → Embedding → (n, 100, 300) → BiLSTM → Dense → Sigmoid
SHAP approach:
Step 1: Manually look up embeddings: tokens → float embeddings (n, 100, 300)
Step 2: Run GradientExplainer on sub-model: embeddings → BiLSTM → Dense → Sigmoid
Step 3: SHAP values shape = (n, 100, 300) — one value per token per embedding dim
Step 4: Sum across 300 embedding dims → (n, 100) — one value per token position
Step 5: Map token IDs → words and aggregate mean SHAP per word
A positive SHAP value means the word pushes the prediction toward hate speech.
A negative SHAP value means the word pushes the prediction toward non-hate.
Output per Model
For each of the 7 models (6 v1 + 1 v2), evaluated on 4 test sets (English, Hindi, Hinglish, Full):
- Top-20 word importance bar chart —
shap_topwords_{lang}.png
- Top-50 words CSV —
shap_topwords_{lang}.csv
- Summary CSV — top-5 hate/non-hate words per eval language
2. v1 — All 6 Strategies
Strategy 1: English → Hindi → Hinglish
| Eval |
Top Hate Words |
Top Non-Hate Words |
| English |
blame, cretin, blaming, unhelpful, upwards |
nt, wwf, facebook, ahh, cum |
| Hindi |
रे, पढ़ने, लाइव, गाला, औखत |
आखिरकार, मुख, बिकुल, शायद, ह |
| Hinglish |
nawaz, dhawan, bashing, shareef, scn |
gau, age, rajya, chori, channels |
| Full |
molvi, chalo, molana, scn, elitist |
rajya, coding, meat, haan, maine |
| Eval |
Top Words Plot |
| English |
 |
| Hindi |
 |
| Hinglish |
 |
| Full |
 |
Strategy 2: English → Hinglish → Hindi
| Eval |
Top Hate Words |
Top Non-Hate Words |
| English |
grave, svi, vox, ahh, grown |
buried, coon, ane, million, normally |
| Hindi |
नड्डा, हिसक, बड़े, सांसदों, रद्दीके |
समाज, सबकी, सऊदी, समझा, अमिताभ |
| Hinglish |
khi, dada, kiske, srk, chalo |
gau, tk, online, liberty, taraf |
| Full |
dada, roj, shamelessness, tujhe, epic |
akash, sapna, proud, buddy, episcopal |
| Eval |
Top Words Plot |
| English |
 |
| Hindi |
 |
| Hinglish |
 |
| Full |
 |
Strategy 3: Hindi → English → Hinglish ⭐ Best Model (v1)
| Eval |
Top Hate Words |
Top Non-Hate Words |
| English |
credence, bj, rosario, ghazi, eni |
plain, stranger, sarcasm, rubbish, comprise |
| Hindi |
कॉल, भूमिपूजन, लें, आधी, मूर्ख |
मैसेज, बेमन, पुलिसकर्मी, जाएगी, पड़े |
| Hinglish |
bacchi, bull, srk, bahana, behan |
madrassa, zaida, gdp, bech, nd |
| Full |
skua, brut, cleansing, captaincy, baar |
taraf, pussy, directory, quran, kaha |
| Eval |
Top Words Plot |
| English |
 |
| Hindi |
 |
| Hinglish |
 |
| Full |
 |
Strategy 4: Hindi → Hinglish → English
| Eval |
Top Hate Words |
Top Non-Hate Words |
| English |
violence, ahh, potus, spic, undocumented |
beginner, dollars, bih, messages, total |
| Hindi |
जाएगी, दूसरों, इंटरव्यू, हवाई, अक्षय |
नियम, डाला।ये, दर्शन, मुलाकात, उज्ज्वल |
| Hinglish |
tatti, sham, dino, roko, krk |
lac, online, ancestor, zaida, target |
| Full |
ahh, moi, bj, fault, pan |
asperger, hundred, database, wicked, nam |
| Eval |
Top Words Plot |
| English |
 |
| Hindi |
 |
| Hinglish |
 |
| Full |
 |
Strategy 5: Hinglish → English → Hindi
| Eval |
Top Hate Words |
Top Non-Hate Words |
| English |
bastard, establishes, code, poo, hub |
blatantly, languages, turkey, fags, gear |
| Hindi |
रंजन, गोगोई, नड्डा, सांसदों, पित्त |
चूतिए, मुल्ले, हथियार, उपनिषद, जन्मभूमि |
| Hinglish |
huye, dada, abb, arey, abduction |
rajya, bahu, parliament, code, music |
| Full |
skua, praised, spic, sabse, plz |
liberty, languages, speaks, bache, maine |
| Eval |
Top Words Plot |
| English |
 |
| Hindi |
 |
| Hinglish |
 |
| Full |
 |
Strategy 6: Hinglish → Hindi → English
| Eval |
Top Hate Words |
Top Non-Hate Words |
| English |
opponents, massacres, coon, ahh, fitness |
annie, model, nearly, lloyd, nest |
| Hindi |
लें, अमिताभ, मी, करेंगे, रखता |
आंखें, जे, बुरे, लोगे, जायज़ा |
| Hinglish |
fav, janab, chori, cum, ruk |
online, gau, dehli, 2017, rajya |
| Full |
srk, roj, rhi, purana, aapke |
nest, maine, hone, haired, barrel |
| Eval |
Top Words Plot |
| English |
 |
| Hindi |
 |
| Hinglish |
 |
| Full |
 |
3. v2 — Hinglish → Hindi → English → Full (50 epochs)
| Eval |
Top Hate Words |
Top Non-Hate Words |
| English |
nas, fags, sicko, sabotage, advocating |
grow, barrel, homosexual, pak, join |
| Hindi |
वादा, वैज्ञानिकों, ऐ, उतारा, गला |
जीतेगा, घोंटने, जिहादी, आपत्तिजनक, चमचो |
| Hinglish |
arey, bahir, punish, papa, interior |
online, member, mam, messages, asha |
| Full |
blamed, criticized, syntax, grown, sine |
underneath, smack, online, hole, clue |
| Eval |
Top Words Plot |
| English |
 |
| Hindi |
 |
| Hinglish |
 |
| Full |
 |
4. Cross-Model Comparison
Words that appear in the top-10 SHAP list of at least 3 models, side-by-side across all strategies:
English test set:
Hindi test set:
Hinglish test set:
Full test set:
5. Key Findings
5.1 SHAP Magnitude Reveals Language Confidence
Hindi SHAP values are consistently one order of magnitude smaller than English and Hinglish:
| Language |
Typical Top SHAP |
Interpretation |
| English |
0.03 – 0.08 |
Model is confident — GloVe has rich English vectors |
| Hinglish |
0.03 – 0.07 |
Model learned strong patterns despite OOV words |
| Hindi |
0.002 – 0.005 |
Model is uncertain — most Hindi tokens have zero GloVe vectors |
This directly explains the lower accuracy and F1 on Hindi across all models.
5.2 Consistent Non-Hate Signals Across Models
The word "online" (negative SHAP) and "rajya" (state/parliament, negative SHAP) appear as top non-hate predictors in 4 out of 6 v1 models and v2. These represent informational/political discussion context that the model correctly distinguishes from targeted hate.
5.3 Hate Speech Markers Are Linguistically Coherent
- English: Direct slurs (
spic, coon), violence language (massacres, cleansing), accusatory verbs (blame, blaming, blamed, criticized) — consistent with how hate speech presents in English social media
- Hinglish: Relationship insults (
behan — sister, used in abusive context), aggressive interjections (arey, abb, ruk), names in hate context (srk, dada) — reflects code-mixed abuse patterns
- Hindi: Body/violence metaphors (
गला — throat, as in strangle; मूर्ख — fool) and political provocations (भूमिपूजन — ground-breaking ceremony, polarising event)
5.4 Spurious Correlations Are Visible
Several high-SHAP words are clearly spurious:
- "syntax", "sine", "skua" as hate markers in v2 full eval — rare words the model overfits to in specific hateful contexts rather than learning the word's meaning
- "homosexual" as non-hate in v2 — appears in informational/news articles in the dataset rather than targeted slurs
- "ahh" appearing as hate in multiple models — likely a noise/exclamation pattern co-occurring with aggressive text
These spurious correlations are expected limitations of GloVe + BiLSTM — without contextual embeddings (e.g. BERT), the model cannot distinguish word meaning from co-occurrence patterns.
5.5 v1 vs v2 Comparison
| Aspect |
v1 (8 epochs) |
v2 (50 epochs) |
| English SHAP range |
0.03–0.07 |
0.02–0.06 |
| Hinglish SHAP range |
0.03–0.57 |
0.04–0.46 |
| Hindi SHAP range |
0.001–0.005 |
0.003–0.007 |
| English hate markers |
Varied, some spurious |
More direct: sicko, fags, sabotage, advocating |
| Full eval hate markers |
Mixed language words |
Accusatory framing: blamed, criticized |
v2's longer training produces slightly more semantically coherent English hate markers. The full-dataset phase in v2 notably produces accusatory framing words (blamed, criticized, grown, advocating) as hate predictors — reflecting that hate speech in the combined corpus often frames targets through blame/accusation rather than direct slurs.
